link

Author: ANGELOANTU7

Backend/NotesToText.py Backend/Final_NotesToText.pyBackend/NotesToText.py renamed to Backend/Final_NotesToText.py

@@ -1,5 +1,5 @@
 import os
-from fastapi import APIRouter,UploadFile,File
+from fastapi import APIRouter,UploadFile,File,Form
 from pdf2image import convert_from_path
 from google.cloud import vision
 from typing import List
@@ -22,8 +22,6 @@
 
 
 def pdf_to_images_from_bytes(pdf_content, output_folder, file_name):
-    s3_bucket_name = 'learnmateai'
-    
     # Save PDF content to a temporary file
     with tempfile.NamedTemporaryFile(delete=False) as temp_file:
         temp_filename = temp_file.name
@@ -46,19 +44,14 @@ def pdf_to_images_from_bytes(pdf_content, output_folder, file_name):
         s3.put_object(Body=image_bytes, Bucket=s3_bucket_name, Key=image_key)
 
         image_paths.append(image_key)
-    noImg = i+1     
+    
+    noImg = i + 1
     return image_paths, noImg
 
 
-def convert(s):
-    substring_to_remove = "Scanned by CamScanner"
-    s3_bucket_name = 'learnmateai'
-
-    
-    prefix = s
-    
+def convert(prefix,user):
     # List files in the S3 bucket with the specified prefix
-    response = s3.list_objects_v2(Bucket=s3_bucket_name, Prefix=prefix)
+    response = s3.list_objects_v2(Bucket=s3_bucket_name, Prefix=user+prefix)
 
     # Extract the file names from the response
     files = [obj['Key'] for obj in response.get('Contents', [])]
@@ -67,16 +60,16 @@ def convert(s):
     for file_name in files:
         file_name = os.path.splitext(os.path.basename(file_name))[0]
 
-        print(f"converting {file_name}....")
+        print(f"Converting {file_name}....")
+        
+        # Delete existing files in the output folder
+        output_folder = f'{user}images/Notes_images/{file_name}'
+        delete_folder_objects(output_folder)
 
         # Download the PDF file from S3
-        pdf_object = s3.get_object(Bucket=s3_bucket_name, Key=f'{prefix}{file_name}.pdf')
+        pdf_object = s3.get_object(Bucket=s3_bucket_name, Key=f'{user}{prefix}{file_name}.pdf')
         pdf_content = pdf_object['Body'].read()
 
-        # Create the output folder in S3
-        output_folder = f'images/Notes_images/{file_name}'
-        s3.put_object(Body='', Bucket=s3_bucket_name, Key=f'{output_folder}/')
-        
         # Convert the PDF to images and save them in the output folder in S3
         image_paths, noImg = pdf_to_images_from_bytes(pdf_content, output_folder, file_name)
         print(noImg)
@@ -98,9 +91,11 @@ def convert(s):
             response = client.text_detection(image=content)
             texts = response.text_annotations[0]
             text = str(texts.description)
-            image_contents += text.replace(substring_to_remove, "")
+            if "Scanned by CamScanner" in text:
+                text = text.replace("Scanned by CamScanner", "")
+            image_contents += text
 
-        s3_key = f'notes_txt/{file_name}.txt'
+        s3_key = f'{user}notes_txt/{file_name}.txt'
 
         # Upload the text content to S3
         s3.put_object(
@@ -116,89 +111,114 @@ def convert(s):
                     response.error.message))
 
 
-@router.get("/notestotext")
-def NotesToText_handler():
+def delete_folder_objects(prefix):
+    # List objects in the S3 bucket with the specified prefix
+    response = s3.list_objects_v2(Bucket=s3_bucket_name, Prefix=prefix)
+    
+    # Extract the object keys from the response
+    objects = [obj['Key'] for obj in response.get('Contents', [])]
+    
+    # Delete each object
+    for obj_key in objects:
+        s3.delete_object(Bucket=s3_bucket_name, Key=obj_key)
 
+
+@router.post("/filestotext2")
+async def NotesToText_handler(user: str = Form(...)):
+    user = user + "/"
     prefix = 'notes_pdf/'
     prefix2 = 'pyqs_pdf/'
-    convert(prefix)
-    convert(prefix2)
-
+    
+    # Delete existing files in the output folders
+    delete_folder_objects(user+'images/Notes_images/')
+    delete_folder_objects(user+'notes_txt/')
+    
+    convert(prefix,user)
+    convert(prefix2,user)
+    
+    return {"process completed"}
 
 
 @router.post("/notestotext_modwise")
-async def upload_files1(files: List[UploadFile] = File(...)):
+async def upload_files1(files: List[UploadFile] = File(...), user: str = Form(...)):
     filenames = []
-
+    user = user + "/"
     for file in files:
         contents = await file.read()
         file_obj = BytesIO(contents)
         try:
             s3.upload_fileobj(
                 file_obj,
                 s3_bucket_name,
-                "notes_pdf/" + file.filename,
+                user + "notes_pdf/" + file.filename,
             )
             filenames.append(file.filename)
         except NoCredentialsError:
             return {"error": "AWS credentials not found."}
 
     return {"filenames": filenames}
 
+
 @router.post("/notestotext_syllabus")
-async def upload_files2(files: List[UploadFile] = File(...)):
+async def upload_files2(files: List[UploadFile] = File(...), user: str = Form(...)):
     filenames = []
+    user = user + "/"
     for file in files:
         contents = await file.read()
         file_obj = BytesIO(contents)
         try:
             s3.upload_fileobj(
                 file_obj,
                 s3_bucket_name,
-                "syllabus_pdf/" + file.filename,
+                user + "syllabus_txt/" + file.filename,
             )
             filenames.append(file.filename)
         except NoCredentialsError:
             return {"error": "AWS credentials not found."}
 
     return {"filenames": filenames}
 
+
 @router.post("/notestotext_pyqs")
-async def upload_files3(files: List[UploadFile] = File(...)):
+async def upload_files3(files: List[UploadFile] = File(...), user: str = Form(...)):
     filenames = []
+    user = user + "/"
     for file in files:
         contents = await file.read()
         file_obj = BytesIO(contents)
         try:
             s3.upload_fileobj(
                 file_obj,
                 s3_bucket_name,
-                "pyqs_pdf/" + file.filename,
+                user + "pyqs_pdf/" + file.filename,
             )
             filenames.append(file.filename)
         except NoCredentialsError:
             return {"error": "AWS credentials not found."}
 
     return {"filenames": filenames}
 
+
 @router.post("/notestotext_anythingelse")
-async def upload_files4(files: List[UploadFile] = File(...)):
+async def upload_files4(files: List[UploadFile] = File(...), user: str = Form(...)):
     filenames = []
+    user = user + "/"
     for file in files:
         contents = await file.read()
         file_obj = BytesIO(contents)
         try:
             s3.upload_fileobj(
                 file_obj,
                 s3_bucket_name,
-                "anything_else/" + file.filename,
+                user + "anything_else/" + file.filename,
             )
             filenames.append(file.filename)
         except NoCredentialsError:
             return {"error": "AWS credentials not found."}
 
     return {"filenames": filenames}
 
+
 @router.get("/")
 async def hello():
-    return {"hello nigga"}
+    return {"Byte 404 rocks"}